alexeytochin/tf_seq2seq_losses

TensorFlow implementations of losses for sequence to sequence machine learning models

34
/ 100
Emerging

This is a TensorFlow library that significantly speeds up the calculation of Connectionist Temporal Classification (CTC) loss functions, which are critical for training machine learning models on sequential data. It takes in model output logits and ground truth labels, and outputs a more accurate and stable loss value much faster than standard TensorFlow. This tool is designed for machine learning engineers and researchers working on sequence-to-sequence problems.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher building models for speech recognition, handwriting recognition, or other sequence-to-sequence tasks and need faster training or stable second-order derivatives for your CTC loss calculations.

Not ideal if you are not working with TensorFlow or if your machine learning problem does not involve sequence-to-sequence modeling with CTC loss.

sequence-to-sequence-modeling speech-recognition handwriting-recognition deep-learning-optimization neural-network-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

10

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Jun 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/alexeytochin/tf_seq2seq_losses"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.